A Distribution Network Design Model Using Data Classification and Fleet Optimization

Articles in Press

Authors

1 Department of Industrial Engineering, Faculty of Engineering, Islamic Azad University, North Tehran Branch, Tehran, Iran

2 Department of Industrial Engineering, North Tehran Branch, Islamic Azad University, Tehran, Iran.

3 Department of Mathematics, Faculty of Sciences, Islamic Azad University, North Tehran Branch, Tehran, Iran

Abstract

This study seeks to bridge the existing gaps in previous researches by introducing a
comprehensive data-driven network design model. The process begins with an in-depth analysis
of customer demand, utilizing unsupervised learning algorithms to gain valuable insights into
consumer behavior. This analysis will help identify demand levels across various geographical
regions while uncovering patterns that fluctuate over time. These insights will serve as essential
inputs for the network design model. To facilitate effective data classification and analysis, the
Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm will be
employed, enabling accurate estimation of customer demand based on innovative parameters.
Building upon these findings, a new mathematical model will be created that incorporates fleet
optimization constraints. Importantly, during this modeling process, emphasis will be placed not
only on optimizing the number, location, and capacity of facilities but also on refining fleet types
and their compositions to enhance overall efficiency. Due to the complexity of the model, it will
be solved using various numerical case problems. Due to the complexity of the model, it will be
solved using various numerical case problems. The results demonstrate that the proposed data-
driven model achieves an average profit improvement of 10-15% compared to traditional non-
clustered approaches. Furthermore, the model yields noticeable cost savings of approximately 8-
12% in transportation and fleet-related expenses. Furthermore, the integrated nature of model
allows for an examination of key parameters to extract valuable managerial insights,
demonstrating the synergy between data-driven clustering and mathematical optimization for
distribution network design.

Keywords

Main Subjects

Advances in Industrial Engineering

Articles in Press, Accepted Manuscript
Available Online from 27 September 2025

Files

Share

How to cite

Statistics